Feature-based 3D texture synthesis approach

Numerous 3D textures have been synthesized from 2D textures by mage-based approaches. However, the quality problems still exist for 3D texture synthesis. Further improvements are required to extract more reliable texture features. A well-known texture feature extraction approach is the grey level co-occurrence probability (GLCP) approach. In this paper, a feature-based approach incorporating GLCP features from a 2D texture is presented for 3D texture synthesis. For color feature extraction, appearance vectors are used to replace RGB color values. For GLCP feature extraction, the statistical features including entropy, contrast, and correlation are extracted to exploit spatial relationships. Moreover, a weighting scheme is introduced to obtain weighted color and GLCP features for neighborhood matching in the synthesis process. The experimental results show that the proposed approach performs well in terms of the synthesis quality.